AIF-C01 Fundamentals of AI and ML Practice Question
A machine learning team notices their model performs excellently on the training dataset but poorly on new, unseen data. They want to reduce this gap without collecting more data. Which action most directly addresses the problem?
⚠ Common exam trap
The trap here is assuming that a model performing better on training data will automatically perform better on new data.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Apply regularization techniques such as L2 penalty or dropout
The described pattern is classic overfitting: strong training performance with weak performance on unseen data. Regularization such as L2 penalties or dropout constrains the model and improves generalization. Adding capacity, training longer, or discarding validation all worsen or conceal the issue instead of correcting it.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Apply regularization techniques such as L2 penalty or dropout
Why this is correct
Regularization constrains the model so it cannot fit training noise as easily, which improves generalization to unseen data. L2 penalties shrink weights and dropout randomly deactivates units during training, both discouraging memorization. This directly targets the overfitting gap described without requiring additional data collection.
- ✗
Increase model complexity by adding more layers and parameters
Why it's wrong here
Adding complexity typically widens the gap between training and unseen data performance, because the model memorizes training noise more effectively. The described symptom already indicates the model fits training data too closely, so increasing capacity worsens overfitting rather than reducing it. This action moves in the wrong direction for the stated problem.
- ✗
Train for many more epochs until training loss approaches zero
Why it's wrong here
Driving training loss toward zero means the model fits the training set even more tightly, which usually deepens overfitting and widens the performance gap on new data. More epochs do not add information; they let the model memorize quirks. This action aggravates the exact symptom the team is trying to fix.
- ✗
Remove the validation dataset and evaluate only on training data
Why it's wrong here
Removing validation eliminates the signal that would reveal generalization problems and leaves the team blind to overfitting. Evaluation on training data alone is optimistic by construction and cannot guide corrective action. This choice hides the problem rather than solving the underlying generalization gap.
Go deeper
Related to this question
About these practice questions
One of 862 original AIF-C01 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Amazon Web Services exam blueprint
This AIF-C01 practice question is part of Courseiva's free Amazon Web Services certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AIF-C01 exam.